Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[RLlib] [Release tests] Make rollout fragment length auto for release tests #30079

Merged
merged 6 commits into from
Nov 14, 2022
Merged

[RLlib] [Release tests] Make rollout fragment length auto for release tests #30079

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
ff5fa78
Rollout fragment length must be greater than or equal to n_step
avnishn Nov 8, 2022
da9ca31
Revert change, make rollout_frag length auto
avnishn Nov 8, 2022
27dbdf2
Merge branch 'master' of https://github.com/ray-project/ray into upda…
avnishn Nov 10, 2022
2d6fa91
Make rollout_frag_length automatically determined for ppo
avnishn Nov 10, 2022
5971733
Trigger wheel building
avnishn Nov 11, 2022
87387f2
Remove ipdb for triggering whl building
avnishn Nov 14, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion release/rllib_tests/learning_tests/yaml_files/cql/cql-halfcheetahbulletenv-v0.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,7 @@ cql-halfcheetahbulletenv-v0:
target_entropy: auto
no_done_at_end: false
n_step: 3
rollout_fragment_length: 1
rollout_fragment_length: auto
num_workers: 8
grad_clip: 40
train_batch_size: 256
Expand Down
2 changes: 1 addition & 1 deletion release/rllib_tests/learning_tests/yaml_files/ddpg/ddpg-hopperbulletenv-v0.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,6 +11,7 @@ ddpg-hopperbulletenv-v0:
actor_hiddens: [256, 256]
critic_hiddens: [256, 256]
n_step: 3
rollout_fragment_length: auto
model: {}
gamma: 0.99
env_config: {}
Expand Down Expand Up @@ -38,7 +39,6 @@ ddpg-hopperbulletenv-v0:
use_huber: true
huber_threshold: 1.0
l2_reg: 0.000001
rollout_fragment_length: 1
train_batch_size: 48
num_gpus: 1
num_workers: 0
Expand Down
2 changes: 1 addition & 1 deletion release/rllib_tests/learning_tests/yaml_files/ppo/ppo-breakoutnoframeskip-v4.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,7 @@ ppo-breakoutnoframeskip-v4:
vf_clip_param: 10.0
entropy_coeff: 0.01
train_batch_size: 5000
rollout_fragment_length: 100
rollout_fragment_length: auto
sgd_minibatch_size: 500
num_sgd_iter: 10
num_workers: 30
Expand Down
2 changes: 1 addition & 1 deletion release/rllib_tests/learning_tests/yaml_files/sac/sac-halfcheetahbulletenv-v0.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,7 +20,7 @@ sac-halfcheetahbulletenv-v0:
target_entropy: auto
no_done_at_end: false
n_step: 3
rollout_fragment_length: 1
rollout_fragment_length: auto
train_batch_size: 256
target_network_update_freq: 1
min_sample_timesteps_per_iteration: 1000
Expand Down